update model card README.md

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0259
-- Precision: 0.9947
-- Recall: 0.9947
+- Loss: 0.0242
+- Precision: 0.9935
+- Recall: 0.9934
 
 ## Model description
 
@@ -45,14 +45,15 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 100
-- num_epochs: 2
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
-| 0.1186        | 1.0   | 190  | 0.0757          | 0.9789    | 0.9775 |
-| 0.0392        | 2.0   | 380  | 0.0259          | 0.9947    | 0.9947 |
+| 0.1176        | 1.0   | 190  | 0.0644          | 0.9836    | 0.9828 |
+| 0.0515        | 2.0   | 380  | 0.0281          | 0.9934    | 0.9934 |
+| 0.0189        | 3.0   | 570  | 0.0242          | 0.9935    | 0.9934 |
 
 
 ### Framework versions